ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2406.11686
29
2

The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation

17 June 2024
Noah Golowich
Ankur Moitra
    OffRL
ArXivPDFHTML
Abstract

In this paper, we study the offline RL problem with linear function approximation. Our main structural assumption is that the MDP has low inherent Bellman error, which stipulates that linear value functions have linear Bellman backups with respect to the greedy policy. This assumption is natural in that it is essentially the minimal assumption required for value iteration to succeed. We give a computationally efficient algorithm which succeeds under a single-policy coverage condition on the dataset, namely which outputs a policy whose value is at least that of any policy which is well-covered by the dataset. Even in the setting when the inherent Bellman error is 0 (termed linear Bellman completeness), our algorithm yields the first known guarantee under single-policy coverage. In the setting of positive inherent Bellman error εBE>0{\varepsilon_{\mathrm{BE}}} > 0εBE​>0, we show that the suboptimality error of our algorithm scales with εBE\sqrt{\varepsilon_{\mathrm{BE}}}εBE​​. Furthermore, we prove that the scaling of the suboptimality with εBE\sqrt{\varepsilon_{\mathrm{BE}}}εBE​​ cannot be improved for any algorithm. Our lower bound stands in contrast to many other settings in reinforcement learning with misspecification, where one can typically obtain performance that degrades linearly with the misspecification error.

View on arXiv
Comments on this paper